skills/alibaba/neug/sync-modules/Gen Agent Trust Hub

sync-modules

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to view issue lists, create new issues, and execute GraphQL mutations (gh api graphql) for managing sub-issue relationships.\n- [PROMPT_INJECTION]: The skill processes untrusted data from local markdown files to populate GitHub issues, creating a surface for indirect prompt injection.\n
  • Ingestion points: File content is read from ./specs/[###-feature-name]/tasks/metadata.md and various module_i.md files (Steps 1 and 3).\n
  • Boundary markers: No explicit markers or delimiters are present to separate instructions from the content being processed.\n
  • Capability inventory: The skill possesses write access to GitHub via the gh tool, including issue creation and relationship modification.\n
  • Sanitization: There is no evidence of validation or sanitization of the markdown content before it is used to populate issue titles and bodies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 10:28 AM
Security Audit — agent-trust-hub — sync-modules